Grammatical Error Correction With Neural Reinforcement Learning
Keisuke Sakaguchi, Matt Post, Benjamin van Durme . Arxiv 2017 – 59 citations
We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC). Unlike conventional maximum likelihood estimation (MLE), the model directly optimizes towards an objective that considers a sentence-level, task-specific evaluation metric, avoiding the exposure bias issue in MLE. We demonstrate that NRL outperforms MLE both in human and automated evaluation metrics, achieving the state-of-the-art on a fluency-oriented GEC corpus.